import numpy as np
import seaborn as sns
import pandas as pd
import matplotlib.pyplot as plt
sns.set(style='darkgrid')

df = pd.read_csv('winequality-red.csv')

df.head()

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality
0	7.4	0.70	0.00	1.9	0.076	11.0	34.0	0.9978	3.51	0.56	9.4	5
1	7.8	0.88	0.00	2.6	0.098	25.0	67.0	0.9968	3.20	0.68	9.8	5
2	7.8	0.76	0.04	2.3	0.092	15.0	54.0	0.9970	3.26	0.65	9.8	5
3	11.2	0.28	0.56	1.9	0.075	17.0	60.0	0.9980	3.16	0.58	9.8	6
4	7.4	0.70	0.00	1.9	0.076	11.0	34.0	0.9978	3.51	0.56	9.4	5

df.columns

Index(['fixed acidity', 'volatile acidity', 'citric acid', 'residual sugar',
       'chlorides', 'free sulfur dioxide', 'total sulfur dioxide', 'density',
       'pH', 'sulphates', 'alcohol', 'quality'],
      dtype='object')

df.shape

(1599, 12)

df.isna().sum()

fixed acidity           0
volatile acidity        0
citric acid             0
residual sugar          0
chlorides               0
free sulfur dioxide     0
total sulfur dioxide    0
density                 0
pH                      0
sulphates               0
alcohol                 0
quality                 0
dtype: int64

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1599 entries, 0 to 1598
Data columns (total 12 columns):
 #   Column                Non-Null Count  Dtype  
---  ------                --------------  -----  
 0   fixed acidity         1599 non-null   float64
 1   volatile acidity      1599 non-null   float64
 2   citric acid           1599 non-null   float64
 3   residual sugar        1599 non-null   float64
 4   chlorides             1599 non-null   float64
 5   free sulfur dioxide   1599 non-null   float64
 6   total sulfur dioxide  1599 non-null   float64
 7   density               1599 non-null   float64
 8   pH                    1599 non-null   float64
 9   sulphates             1599 non-null   float64
 10  alcohol               1599 non-null   float64
 11  quality               1599 non-null   int64  
dtypes: float64(11), int64(1)
memory usage: 150.0 KB

df.describe()

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality
count	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000	1599.000000
mean	8.319637	0.527821	0.270976	2.538806	0.087467	15.874922	46.467792	0.996747	3.311113	0.658149	10.422983	5.636023
std	1.741096	0.179060	0.194801	1.409928	0.047065	10.460157	32.895324	0.001887	0.154386	0.169507	1.065668	0.807569
min	4.600000	0.120000	0.000000	0.900000	0.012000	1.000000	6.000000	0.990070	2.740000	0.330000	8.400000	3.000000
25%	7.100000	0.390000	0.090000	1.900000	0.070000	7.000000	22.000000	0.995600	3.210000	0.550000	9.500000	5.000000
50%	7.900000	0.520000	0.260000	2.200000	0.079000	14.000000	38.000000	0.996750	3.310000	0.620000	10.200000	6.000000
75%	9.200000	0.640000	0.420000	2.600000	0.090000	21.000000	62.000000	0.997835	3.400000	0.730000	11.100000	6.000000
max	15.900000	1.580000	1.000000	15.500000	0.611000	72.000000	289.000000	1.003690	4.010000	2.000000	14.900000	8.000000

corr = df.corr()
corr.style.background_gradient(cmap='coolwarm')

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality
fixed acidity	1.000000	-0.256131	0.671703	0.114777	0.093705	-0.153794	-0.113181	0.668047	-0.682978	0.183006	-0.061668	0.124052
volatile acidity	-0.256131	1.000000	-0.552496	0.001918	0.061298	-0.010504	0.076470	0.022026	0.234937	-0.260987	-0.202288	-0.390558
citric acid	0.671703	-0.552496	1.000000	0.143577	0.203823	-0.060978	0.035533	0.364947	-0.541904	0.312770	0.109903	0.226373
residual sugar	0.114777	0.001918	0.143577	1.000000	0.055610	0.187049	0.203028	0.355283	-0.085652	0.005527	0.042075	0.013732
chlorides	0.093705	0.061298	0.203823	0.055610	1.000000	0.005562	0.047400	0.200632	-0.265026	0.371260	-0.221141	-0.128907
free sulfur dioxide	-0.153794	-0.010504	-0.060978	0.187049	0.005562	1.000000	0.667666	-0.021946	0.070377	0.051658	-0.069408	-0.050656
total sulfur dioxide	-0.113181	0.076470	0.035533	0.203028	0.047400	0.667666	1.000000	0.071269	-0.066495	0.042947	-0.205654	-0.185100
density	0.668047	0.022026	0.364947	0.355283	0.200632	-0.021946	0.071269	1.000000	-0.341699	0.148506	-0.496180	-0.174919
pH	-0.682978	0.234937	-0.541904	-0.085652	-0.265026	0.070377	-0.066495	-0.341699	1.000000	-0.196648	0.205633	-0.057731
sulphates	0.183006	-0.260987	0.312770	0.005527	0.371260	0.051658	0.042947	0.148506	-0.196648	1.000000	0.093595	0.251397
alcohol	-0.061668	-0.202288	0.109903	0.042075	-0.221141	-0.069408	-0.205654	-0.496180	0.205633	0.093595	1.000000	0.476166
quality	0.124052	-0.390558	0.226373	0.013732	-0.128907	-0.050656	-0.185100	-0.174919	-0.057731	0.251397	0.476166	1.000000

pH needs to be removed because it not correlated to the target variable and is highly correlated to the

x1 = df[[ 'volatile acidity', 'residual sugar',
       'chlorides', 'total sulfur dioxide', 'density','citric acid',
       'sulphates', 'alcohol','quality']]
y1 = df['quality']

corr = x1.corr()
corr.style.background_gradient(cmap='coolwarm')

	volatile acidity	residual sugar	chlorides	total sulfur dioxide	density	citric acid	sulphates	alcohol	quality
volatile acidity	1.000000	0.001918	0.061298	0.076470	0.022026	-0.552496	-0.260987	-0.202288	-0.390558
residual sugar	0.001918	1.000000	0.055610	0.203028	0.355283	0.143577	0.005527	0.042075	0.013732
chlorides	0.061298	0.055610	1.000000	0.047400	0.200632	0.203823	0.371260	-0.221141	-0.128907
total sulfur dioxide	0.076470	0.203028	0.047400	1.000000	0.071269	0.035533	0.042947	-0.205654	-0.185100
density	0.022026	0.355283	0.200632	0.071269	1.000000	0.364947	0.148506	-0.496180	-0.174919
citric acid	-0.552496	0.143577	0.203823	0.035533	0.364947	1.000000	0.312770	0.109903	0.226373
sulphates	-0.260987	0.005527	0.371260	0.042947	0.148506	0.312770	1.000000	0.093595	0.251397
alcohol	-0.202288	0.042075	-0.221141	-0.205654	-0.496180	0.109903	0.093595	1.000000	0.476166
quality	-0.390558	0.013732	-0.128907	-0.185100	-0.174919	0.226373	0.251397	0.476166	1.000000

corr = x1.corr()
corr.style.background_gradient(cmap='coolwarm')

	volatile acidity	residual sugar	chlorides	total sulfur dioxide	density	citric acid	sulphates	alcohol	quality
volatile acidity	1.000000	0.001918	0.061298	0.076470	0.022026	-0.552496	-0.260987	-0.202288	-0.390558
residual sugar	0.001918	1.000000	0.055610	0.203028	0.355283	0.143577	0.005527	0.042075	0.013732
chlorides	0.061298	0.055610	1.000000	0.047400	0.200632	0.203823	0.371260	-0.221141	-0.128907
total sulfur dioxide	0.076470	0.203028	0.047400	1.000000	0.071269	0.035533	0.042947	-0.205654	-0.185100
density	0.022026	0.355283	0.200632	0.071269	1.000000	0.364947	0.148506	-0.496180	-0.174919
citric acid	-0.552496	0.143577	0.203823	0.035533	0.364947	1.000000	0.312770	0.109903	0.226373
sulphates	-0.260987	0.005527	0.371260	0.042947	0.148506	0.312770	1.000000	0.093595	0.251397
alcohol	-0.202288	0.042075	-0.221141	-0.205654	-0.496180	0.109903	0.093595	1.000000	0.476166
quality	-0.390558	0.013732	-0.128907	-0.185100	-0.174919	0.226373	0.251397	0.476166	1.000000

corr = x1.corr()
corr.style.background_gradient(cmap='coolwarm')

	volatile acidity	residual sugar	chlorides	total sulfur dioxide	density	citric acid	sulphates	alcohol	quality
volatile acidity	1.000000	0.001918	0.061298	0.076470	0.022026	-0.552496	-0.260987	-0.202288	-0.390558
residual sugar	0.001918	1.000000	0.055610	0.203028	0.355283	0.143577	0.005527	0.042075	0.013732
chlorides	0.061298	0.055610	1.000000	0.047400	0.200632	0.203823	0.371260	-0.221141	-0.128907
total sulfur dioxide	0.076470	0.203028	0.047400	1.000000	0.071269	0.035533	0.042947	-0.205654	-0.185100
density	0.022026	0.355283	0.200632	0.071269	1.000000	0.364947	0.148506	-0.496180	-0.174919
citric acid	-0.552496	0.143577	0.203823	0.035533	0.364947	1.000000	0.312770	0.109903	0.226373
sulphates	-0.260987	0.005527	0.371260	0.042947	0.148506	0.312770	1.000000	0.093595	0.251397
alcohol	-0.202288	0.042075	-0.221141	-0.205654	-0.496180	0.109903	0.093595	1.000000	0.476166
quality	-0.390558	0.013732	-0.128907	-0.185100	-0.174919	0.226373	0.251397	0.476166	1.000000

sns.relplot(x="fixed acidity", y="density",data=df)

<seaborn.axisgrid.FacetGrid at 0x2a592d09940>

sns.relplot(x="volatile acidity", y="density",size="quality", sizes=(20,100), hue="quality",data=df)

<seaborn.axisgrid.FacetGrid at 0x2a593129fa0>

sns.relplot(x = "citric acid", y = "pH", hue = "alcohol", col = "quality", data = df);

df.groupby('quality')['fixed acidity'].sum().reset_index()

	quality	fixed acidity
0	3	83.6
1	4	412.3
2	5	5561.9
3	6	5325.5
4	7	1765.6
5	8	154.2

df.groupby('quality')['volatile acidity'].sum().reset_index()

	quality	volatile acidity
0	3	8.845
1	4	36.780
2	5	392.965
3	6	317.395
4	7	80.380
5	8	7.620

df.groupby('quality')['citric acid'].sum().reset_index()

	quality	citric acid
0	3	1.71
1	4	9.23
2	5	165.95
3	6	174.70
4	7	74.66
5	8	7.04

df.groupby('quality')['residual sugar'].sum().reset_index()

	quality	residual sugar
0	3	26.35
1	4	142.80
2	5	1722.15
3	6	1580.45
4	7	541.40
5	8	46.40

df.groupby('quality')['chlorides'].sum().reset_index()

	quality	chlorides
0	3	1.225
1	4	4.806
2	5	63.153
3	6	54.202
4	7	15.241
5	8	1.232

df.groupby('quality')['free sulfur dioxide'].sum().reset_index()

	quality	free sulfur dioxide
0	3	110.0
1	4	650.0
2	5	11566.0
3	6	10024.0
4	7	2795.0
5	8	239.0

df.groupby('quality')['total sulfur dioxide'].sum().reset_index()

	quality	total sulfur dioxide
0	3	249.0
1	4	1921.0
2	5	38486.0
3	6	26075.0
4	7	6969.0
5	8	602.0

df.groupby('quality')['density'].sum().reset_index()

	quality	density
0	3	9.97464
1	4	52.81675
2	5	679.02757
3	6	635.84041
4	7	198.22475
5	8	17.91382

df.groupby('quality')['pH'].sum().reset_index()

	quality	pH
0	3	33.98
1	4	179.22
2	5	2250.67
3	6	2116.93
4	7	654.86
5	8	58.81

df.groupby('quality')['sulphates'].sum().reset_index()

	quality	sulphates
0	3	5.70
1	4	31.61
2	5	422.88
3	6	430.86
4	7	147.51
5	8	13.82

df.groupby('quality')['alcohol'].sum().reset_index()

	quality	alcohol
0	3	99.550000
1	4	544.050000
2	5	6741.700000
3	6	6781.633333
4	7	2281.716667
5	8	217.700000

Categorical plots

sns.catplot(x='quality',y='residual sugar',data=df)

<seaborn.axisgrid.FacetGrid at 0x2a593b013d0>

We cannot use swarmplot in this dataset because all the variables are continuous and only the quality variable is discrete

sns.boxenplot(x="quality",y="chlorides",data=df)

<AxesSubplot:xlabel='quality', ylabel='chlorides'>

sns.boxplot(x="quality",y="density",data=df)

<AxesSubplot:xlabel='quality', ylabel='density'>

sns.violinplot(x ="quality", y = "alcohol", data = df)

<AxesSubplot:xlabel='quality', ylabel='alcohol'>

sns.violinplot(x="quality", y="free sulfur dioxide", bw=.25, split=True, palette= "pastel", inner= "stick", data=df)

<AxesSubplot:xlabel='quality', ylabel='free sulfur dioxide'>

sns.barplot(x="quality",y="total sulfur dioxide",palette = "ch:.25",data=df)

<AxesSubplot:xlabel='quality', ylabel='total sulfur dioxide'>

sns.pointplot(x = "quality", y = "alcohol", data= df)

<AxesSubplot:xlabel='quality', ylabel='alcohol'>

Additional Plots that is not done in class

sns.kdeplot(data=df, x="quality", multiple="layer") #kde=kernal density estimation

<AxesSubplot:xlabel='quality', ylabel='Density'>

df.quality.plot(kind='hist',edgecolor='black')

<AxesSubplot:ylabel='Frequency'>

sns.pairplot(data=df, hue="quality")

<seaborn.axisgrid.PairGrid at 0x2a593e36df0>

sns.stripplot(x="quality", y="chlorides", data=df)

<AxesSubplot:xlabel='quality', ylabel='chlorides'>

sns.scatterplot(data=df, x="pH", y="density")
sns.rugplot(data=df, x="pH", y="density")

<AxesSubplot:xlabel='pH', ylabel='density'>

sns.ecdfplot(data=df, y="quality")

<AxesSubplot:xlabel='Proportion', ylabel='quality'>

Automated EDA

1. SweetViz

import sweetviz as sv
sweet_report = sv.analyze(df)
sweet_report.show_html('sweetviz_report.html')

Report sweetviz_report.html was generated! NOTEBOOK/COLAB USERS: the web browser MAY not pop up, regardless, the report IS saved in your notebook/colab files.

1. AutoViz

from autoviz.AutoViz_Class import AutoViz_Class
AV = AutoViz_Class()
df = AV.AutoViz('winequality-red.csv')

Shape of your Data Set loaded: (1599, 12)
#######################################################################################
######################## C L A S S I F Y I N G  V A R I A B L E S  ####################
#######################################################################################
Classifying variables in data set...
    12 Predictors classified...
        No variables removed since no ID or low-information variables found in data set
Number of All Scatter Plots = 66
Time to run AutoViz = 6 seconds 

 ###################### AUTO VISUALIZATION Completed ########################